Instructions to use mistral-experimental/pixtral-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistral-experimental/pixtral-12b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="mistral-experimental/pixtral-12b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mistral-experimental/pixtral-12b")
model = AutoModelForMultimodalLM.from_pretrained("mistral-experimental/pixtral-12b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mistral-experimental/pixtral-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mistral-experimental/pixtral-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-experimental/pixtral-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/mistral-experimental/pixtral-12b

SGLang

How to use mistral-experimental/pixtral-12b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mistral-experimental/pixtral-12b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-experimental/pixtral-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mistral-experimental/pixtral-12b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-experimental/pixtral-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mistral-experimental/pixtral-12b with Docker Model Runner:
```
docker model run hf.co/mistral-experimental/pixtral-12b
```

How do I load the model quantized?

#33

by treehugg3 - opened Apr 10, 2025

Discussion

treehugg3

Apr 10, 2025

•

edited Apr 10, 2025

I'm getting CUDA OOM issues and it complains about tensors being on different devices when I set a device map to include CPU. Is there an easy way I can load the model with 8-bit precision?

If I try this:

quantization_config = BitsAndBytesConfig(load_in_8bit=True)
model = LlavaForConditionalGeneration.from_pretrained(".", device_map="auto", quantization_config=quantization_config)

I get this error:

Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

Also happens when I configure AutoProcessor with a quantization_config...

nielsr

Apr 10, 2025

Pinging @RaushanTurganbay here

RaushanTurganbay

Apr 10, 2025

@treehugg3 can you show the whole inference script? Looks like you didn't cast inputs to fp16 before inference which is the dtype used by BnB by default

treehugg3

Apr 10, 2025

•

edited Apr 10, 2025

Thank you for helping. Here is the script I used:

from transformers import LlavaForConditionalGeneration, AutoProcessor, BitsAndBytesConfig
from PIL import Image

model_id="../pixtral-12b"
image_url ="https://m.media-amazon.com/images/I/81tPIA63TrL._AC_SL1500_.jpg"
prompt = "Describe the picture in one sentence."

IMG_URLS = [
    "https://picsum.photos/id/237/400/300",
    "https://picsum.photos/id/231/200/300",
    "https://picsum.photos/id/27/500/500",
    "https://picsum.photos/id/17/150/600",
]
PROMPT = "<s>[INST]Describe the pictures.\n[IMG][IMG][IMG][IMG][/INST]"

quantization_config = BitsAndBytesConfig(load_in_8bit=True)
model = LlavaForConditionalGeneration.from_pretrained(model_id, device_map="auto", quantization_config=quantization_config)
processor = AutoProcessor.from_pretrained(model_id)

inputs = processor(images=IMG_URLS, text=PROMPT, return_tensors="pt").to("cuda")
generate_ids = model.generate(**inputs, max_new_tokens=500, torch_dtype="auto")
output = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
print(output)

It turns out that by creating a new virtualenv, this code now runs properly. There must have been some strange package version combination that caused it to fail in the other one. Really sorry for bothering, I spent a long time trying to figure out why it wasn't working, but it works great now!

RaushanTurganbay

Apr 11, 2025

Yeah, this has to be casted manually as follows:

inputs = processor(images=IMG_URLS, text=PROMPT, return_tensors="pt").to("cuda", dtype=torch.float16)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment